andrewbai commited on
Commit
b49e65d
1 Parent(s): 09ff57d

Model save

Browse files
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: tinyllama-sft-wizardlm_evol_instruct_v2-full
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # tinyllama-sft-wizardlm_evol_instruct_v2-full
17
+
18
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.7234
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 4
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 128
47
+ - total_eval_batch_size: 32
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 1
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:-----:|:----:|:---------------:|
57
+ | 0.735 | 1.0 | 781 | 0.7234 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.39.0.dev0
63
+ - Pytorch 2.2.2+cu121
64
+ - Datasets 2.14.6
65
+ - Tokenizers 0.15.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.7476945167619654,
4
+ "train_runtime": 7284.6392,
5
+ "train_samples": 99999,
6
+ "train_samples_per_second": 13.727,
7
+ "train_steps_per_second": 0.107
8
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:957fcc07a635456a65c3b20124ee513309f6b470bc7092695b5b1eebb5fd12f4
3
  size 2200119864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85b5fca5ca44b5117118809f941d266cd516ae3453aa5340fd3ba95b762f350
3
  size 2200119864
runs/Apr14_16-21-00_nova.cs.ucla.edu/events.out.tfevents.1713137287.nova.cs.ucla.edu.3519625.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d5309c6b8d08d4078a0750d065af42243ef22f6311fbaafc0e47b7c97b9739
3
- size 34503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a537c1d7f3ca5c23885d11e123a748053c69b073035c2597ae79d6b6989540ce
3
+ size 38504
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.7476945167619654,
4
+ "train_runtime": 7284.6392,
5
+ "train_samples": 99999,
6
+ "train_samples_per_second": 13.727,
7
+ "train_steps_per_second": 0.107
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.999360204734485,
5
+ "eval_steps": 500,
6
+ "global_step": 781,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 6.218732532974693,
14
+ "learning_rate": 2.5316455696202533e-07,
15
+ "loss": 1.0548,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 6.057508328025577,
21
+ "learning_rate": 1.2658227848101267e-06,
22
+ "loss": 1.0608,
23
+ "step": 5
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 6.634383000711397,
28
+ "learning_rate": 2.5316455696202535e-06,
29
+ "loss": 1.0311,
30
+ "step": 10
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 42.22599030062134,
35
+ "learning_rate": 3.7974683544303802e-06,
36
+ "loss": 0.9446,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "grad_norm": 1.6255048263910823,
42
+ "learning_rate": 5.063291139240507e-06,
43
+ "loss": 0.855,
44
+ "step": 20
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 1.223041853621419,
49
+ "learning_rate": 6.329113924050634e-06,
50
+ "loss": 0.8515,
51
+ "step": 25
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 1.1499117468328068,
56
+ "learning_rate": 7.5949367088607605e-06,
57
+ "loss": 0.8538,
58
+ "step": 30
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 0.9893284992712339,
63
+ "learning_rate": 8.860759493670886e-06,
64
+ "loss": 0.8499,
65
+ "step": 35
66
+ },
67
+ {
68
+ "epoch": 0.05,
69
+ "grad_norm": 1.0330597408673325,
70
+ "learning_rate": 1.0126582278481014e-05,
71
+ "loss": 0.8349,
72
+ "step": 40
73
+ },
74
+ {
75
+ "epoch": 0.06,
76
+ "grad_norm": 0.9454728301913932,
77
+ "learning_rate": 1.139240506329114e-05,
78
+ "loss": 0.8139,
79
+ "step": 45
80
+ },
81
+ {
82
+ "epoch": 0.06,
83
+ "grad_norm": 0.867009450049442,
84
+ "learning_rate": 1.2658227848101268e-05,
85
+ "loss": 0.7961,
86
+ "step": 50
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "grad_norm": 0.9233088577396095,
91
+ "learning_rate": 1.3924050632911395e-05,
92
+ "loss": 0.8041,
93
+ "step": 55
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "grad_norm": 0.897730187587102,
98
+ "learning_rate": 1.5189873417721521e-05,
99
+ "loss": 0.8009,
100
+ "step": 60
101
+ },
102
+ {
103
+ "epoch": 0.08,
104
+ "grad_norm": 0.9115211129634383,
105
+ "learning_rate": 1.6455696202531647e-05,
106
+ "loss": 0.7969,
107
+ "step": 65
108
+ },
109
+ {
110
+ "epoch": 0.09,
111
+ "grad_norm": 0.9078252304377841,
112
+ "learning_rate": 1.7721518987341772e-05,
113
+ "loss": 0.8128,
114
+ "step": 70
115
+ },
116
+ {
117
+ "epoch": 0.1,
118
+ "grad_norm": 0.8821431725791585,
119
+ "learning_rate": 1.89873417721519e-05,
120
+ "loss": 0.7563,
121
+ "step": 75
122
+ },
123
+ {
124
+ "epoch": 0.1,
125
+ "grad_norm": 0.8438829745337315,
126
+ "learning_rate": 1.999989986294826e-05,
127
+ "loss": 0.794,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 0.11,
132
+ "grad_norm": 0.9429490146138716,
133
+ "learning_rate": 1.9996395276708856e-05,
134
+ "loss": 0.7879,
135
+ "step": 85
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "grad_norm": 1.0152173886159006,
140
+ "learning_rate": 1.9987885843187717e-05,
141
+ "loss": 0.788,
142
+ "step": 90
143
+ },
144
+ {
145
+ "epoch": 0.12,
146
+ "grad_norm": 0.9186368798898343,
147
+ "learning_rate": 1.9974375822762117e-05,
148
+ "loss": 0.7707,
149
+ "step": 95
150
+ },
151
+ {
152
+ "epoch": 0.13,
153
+ "grad_norm": 0.8971041378168991,
154
+ "learning_rate": 1.9955871979429188e-05,
155
+ "loss": 0.7664,
156
+ "step": 100
157
+ },
158
+ {
159
+ "epoch": 0.13,
160
+ "grad_norm": 0.9008904434552364,
161
+ "learning_rate": 1.9932383577419432e-05,
162
+ "loss": 0.8074,
163
+ "step": 105
164
+ },
165
+ {
166
+ "epoch": 0.14,
167
+ "grad_norm": 1.028657752464771,
168
+ "learning_rate": 1.9903922376558432e-05,
169
+ "loss": 0.7919,
170
+ "step": 110
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "grad_norm": 0.9517557420940557,
175
+ "learning_rate": 1.9870502626379127e-05,
176
+ "loss": 0.7998,
177
+ "step": 115
178
+ },
179
+ {
180
+ "epoch": 0.15,
181
+ "grad_norm": 0.9048840711577915,
182
+ "learning_rate": 1.983214105898757e-05,
183
+ "loss": 0.7804,
184
+ "step": 120
185
+ },
186
+ {
187
+ "epoch": 0.16,
188
+ "grad_norm": 0.9111504895861703,
189
+ "learning_rate": 1.978885688068572e-05,
190
+ "loss": 0.7538,
191
+ "step": 125
192
+ },
193
+ {
194
+ "epoch": 0.17,
195
+ "grad_norm": 0.902524854174019,
196
+ "learning_rate": 1.9740671762355548e-05,
197
+ "loss": 0.7566,
198
+ "step": 130
199
+ },
200
+ {
201
+ "epoch": 0.17,
202
+ "grad_norm": 0.9110302651471653,
203
+ "learning_rate": 1.9687609828609156e-05,
204
+ "loss": 0.7737,
205
+ "step": 135
206
+ },
207
+ {
208
+ "epoch": 0.18,
209
+ "grad_norm": 0.9438921387685624,
210
+ "learning_rate": 1.9629697645710432e-05,
211
+ "loss": 0.7561,
212
+ "step": 140
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "grad_norm": 0.8687548609010227,
217
+ "learning_rate": 1.9566964208274254e-05,
218
+ "loss": 0.7564,
219
+ "step": 145
220
+ },
221
+ {
222
+ "epoch": 0.19,
223
+ "grad_norm": 0.9360336326575724,
224
+ "learning_rate": 1.9499440924749878e-05,
225
+ "loss": 0.7616,
226
+ "step": 150
227
+ },
228
+ {
229
+ "epoch": 0.2,
230
+ "grad_norm": 0.9291842110885165,
231
+ "learning_rate": 1.9427161601695833e-05,
232
+ "loss": 0.7587,
233
+ "step": 155
234
+ },
235
+ {
236
+ "epoch": 0.2,
237
+ "grad_norm": 0.8992521463936806,
238
+ "learning_rate": 1.9350162426854152e-05,
239
+ "loss": 0.7923,
240
+ "step": 160
241
+ },
242
+ {
243
+ "epoch": 0.21,
244
+ "grad_norm": 0.9199465839289203,
245
+ "learning_rate": 1.926848195103242e-05,
246
+ "loss": 0.7567,
247
+ "step": 165
248
+ },
249
+ {
250
+ "epoch": 0.22,
251
+ "grad_norm": 0.9202340634296483,
252
+ "learning_rate": 1.9182161068802742e-05,
253
+ "loss": 0.7561,
254
+ "step": 170
255
+ },
256
+ {
257
+ "epoch": 0.22,
258
+ "grad_norm": 0.8815186951994902,
259
+ "learning_rate": 1.909124299802724e-05,
260
+ "loss": 0.7602,
261
+ "step": 175
262
+ },
263
+ {
264
+ "epoch": 0.23,
265
+ "grad_norm": 0.9374982372632831,
266
+ "learning_rate": 1.8995773258220374e-05,
267
+ "loss": 0.7726,
268
+ "step": 180
269
+ },
270
+ {
271
+ "epoch": 0.24,
272
+ "grad_norm": 0.8668215722574871,
273
+ "learning_rate": 1.8895799647758912e-05,
274
+ "loss": 0.7641,
275
+ "step": 185
276
+ },
277
+ {
278
+ "epoch": 0.24,
279
+ "grad_norm": 0.9704566556440527,
280
+ "learning_rate": 1.879137221995095e-05,
281
+ "loss": 0.7631,
282
+ "step": 190
283
+ },
284
+ {
285
+ "epoch": 0.25,
286
+ "grad_norm": 1.0765530525420333,
287
+ "learning_rate": 1.868254325797594e-05,
288
+ "loss": 0.7602,
289
+ "step": 195
290
+ },
291
+ {
292
+ "epoch": 0.26,
293
+ "grad_norm": 0.8477600964123878,
294
+ "learning_rate": 1.8569367248708343e-05,
295
+ "loss": 0.7696,
296
+ "step": 200
297
+ },
298
+ {
299
+ "epoch": 0.26,
300
+ "grad_norm": 0.8880373428392885,
301
+ "learning_rate": 1.845190085543795e-05,
302
+ "loss": 0.7717,
303
+ "step": 205
304
+ },
305
+ {
306
+ "epoch": 0.27,
307
+ "grad_norm": 0.9054121985443794,
308
+ "learning_rate": 1.8330202889500518e-05,
309
+ "loss": 0.7594,
310
+ "step": 210
311
+ },
312
+ {
313
+ "epoch": 0.28,
314
+ "grad_norm": 0.9241486536472063,
315
+ "learning_rate": 1.8204334280833005e-05,
316
+ "loss": 0.7461,
317
+ "step": 215
318
+ },
319
+ {
320
+ "epoch": 0.28,
321
+ "grad_norm": 0.8883815381945972,
322
+ "learning_rate": 1.807435804746807e-05,
323
+ "loss": 0.7244,
324
+ "step": 220
325
+ },
326
+ {
327
+ "epoch": 0.29,
328
+ "grad_norm": 0.954185859352863,
329
+ "learning_rate": 1.7940339263983112e-05,
330
+ "loss": 0.7546,
331
+ "step": 225
332
+ },
333
+ {
334
+ "epoch": 0.29,
335
+ "grad_norm": 0.9582618105947629,
336
+ "learning_rate": 1.7802345028919728e-05,
337
+ "loss": 0.7673,
338
+ "step": 230
339
+ },
340
+ {
341
+ "epoch": 0.3,
342
+ "grad_norm": 0.9337180429875352,
343
+ "learning_rate": 1.766044443118978e-05,
344
+ "loss": 0.7371,
345
+ "step": 235
346
+ },
347
+ {
348
+ "epoch": 0.31,
349
+ "grad_norm": 1.0151633649691056,
350
+ "learning_rate": 1.7514708515485002e-05,
351
+ "loss": 0.7531,
352
+ "step": 240
353
+ },
354
+ {
355
+ "epoch": 0.31,
356
+ "grad_norm": 0.8996109508979938,
357
+ "learning_rate": 1.736521024670737e-05,
358
+ "loss": 0.7726,
359
+ "step": 245
360
+ },
361
+ {
362
+ "epoch": 0.32,
363
+ "grad_norm": 0.9539154938066643,
364
+ "learning_rate": 1.7212024473438145e-05,
365
+ "loss": 0.7594,
366
+ "step": 250
367
+ },
368
+ {
369
+ "epoch": 0.33,
370
+ "grad_norm": 0.8527276784078115,
371
+ "learning_rate": 1.705522789046377e-05,
372
+ "loss": 0.7608,
373
+ "step": 255
374
+ },
375
+ {
376
+ "epoch": 0.33,
377
+ "grad_norm": 0.9081328398716373,
378
+ "learning_rate": 1.6894899000377462e-05,
379
+ "loss": 0.7626,
380
+ "step": 260
381
+ },
382
+ {
383
+ "epoch": 0.34,
384
+ "grad_norm": 0.8896600535495715,
385
+ "learning_rate": 1.67311180742757e-05,
386
+ "loss": 0.7633,
387
+ "step": 265
388
+ },
389
+ {
390
+ "epoch": 0.35,
391
+ "grad_norm": 0.8828152532467378,
392
+ "learning_rate": 1.65639671115693e-05,
393
+ "loss": 0.7314,
394
+ "step": 270
395
+ },
396
+ {
397
+ "epoch": 0.35,
398
+ "grad_norm": 0.91123554695286,
399
+ "learning_rate": 1.6393529798929103e-05,
400
+ "loss": 0.7568,
401
+ "step": 275
402
+ },
403
+ {
404
+ "epoch": 0.36,
405
+ "grad_norm": 0.7802151937182064,
406
+ "learning_rate": 1.621989146838704e-05,
407
+ "loss": 0.7301,
408
+ "step": 280
409
+ },
410
+ {
411
+ "epoch": 0.36,
412
+ "grad_norm": 0.8417341529900935,
413
+ "learning_rate": 1.6043139054613326e-05,
414
+ "loss": 0.7409,
415
+ "step": 285
416
+ },
417
+ {
418
+ "epoch": 0.37,
419
+ "grad_norm": 0.8874377472816912,
420
+ "learning_rate": 1.586336105139127e-05,
421
+ "loss": 0.7586,
422
+ "step": 290
423
+ },
424
+ {
425
+ "epoch": 0.38,
426
+ "grad_norm": 0.8993804934668429,
427
+ "learning_rate": 1.568064746731156e-05,
428
+ "loss": 0.7612,
429
+ "step": 295
430
+ },
431
+ {
432
+ "epoch": 0.38,
433
+ "grad_norm": 0.8743646519888882,
434
+ "learning_rate": 1.5495089780708062e-05,
435
+ "loss": 0.7208,
436
+ "step": 300
437
+ },
438
+ {
439
+ "epoch": 0.39,
440
+ "grad_norm": 0.8726571855013807,
441
+ "learning_rate": 1.530678089385782e-05,
442
+ "loss": 0.7296,
443
+ "step": 305
444
+ },
445
+ {
446
+ "epoch": 0.4,
447
+ "grad_norm": 0.8216013695365607,
448
+ "learning_rate": 1.5115815086468103e-05,
449
+ "loss": 0.7194,
450
+ "step": 310
451
+ },
452
+ {
453
+ "epoch": 0.4,
454
+ "grad_norm": 0.911275664325399,
455
+ "learning_rate": 1.492228796847385e-05,
456
+ "loss": 0.7436,
457
+ "step": 315
458
+ },
459
+ {
460
+ "epoch": 0.41,
461
+ "grad_norm": 0.8922331403520879,
462
+ "learning_rate": 1.4726296432169095e-05,
463
+ "loss": 0.7009,
464
+ "step": 320
465
+ },
466
+ {
467
+ "epoch": 0.42,
468
+ "grad_norm": 0.8415314327536128,
469
+ "learning_rate": 1.4527938603696376e-05,
470
+ "loss": 0.7563,
471
+ "step": 325
472
+ },
473
+ {
474
+ "epoch": 0.42,
475
+ "grad_norm": 0.8469607469311058,
476
+ "learning_rate": 1.4327313793918362e-05,
477
+ "loss": 0.7254,
478
+ "step": 330
479
+ },
480
+ {
481
+ "epoch": 0.43,
482
+ "grad_norm": 0.8834979947462068,
483
+ "learning_rate": 1.4124522448696407e-05,
484
+ "loss": 0.7516,
485
+ "step": 335
486
+ },
487
+ {
488
+ "epoch": 0.44,
489
+ "grad_norm": 0.8544733801934922,
490
+ "learning_rate": 1.3919666098600753e-05,
491
+ "loss": 0.7511,
492
+ "step": 340
493
+ },
494
+ {
495
+ "epoch": 0.44,
496
+ "grad_norm": 0.8997621369784197,
497
+ "learning_rate": 1.3712847308077737e-05,
498
+ "loss": 0.7395,
499
+ "step": 345
500
+ },
501
+ {
502
+ "epoch": 0.45,
503
+ "grad_norm": 0.8650786485343112,
504
+ "learning_rate": 1.350416962409934e-05,
505
+ "loss": 0.733,
506
+ "step": 350
507
+ },
508
+ {
509
+ "epoch": 0.45,
510
+ "grad_norm": 0.8646529478803704,
511
+ "learning_rate": 1.3293737524320798e-05,
512
+ "loss": 0.7319,
513
+ "step": 355
514
+ },
515
+ {
516
+ "epoch": 0.46,
517
+ "grad_norm": 0.9052937039545919,
518
+ "learning_rate": 1.3081656364772308e-05,
519
+ "loss": 0.7474,
520
+ "step": 360
521
+ },
522
+ {
523
+ "epoch": 0.47,
524
+ "grad_norm": 0.869464472615771,
525
+ "learning_rate": 1.2868032327110904e-05,
526
+ "loss": 0.7373,
527
+ "step": 365
528
+ },
529
+ {
530
+ "epoch": 0.47,
531
+ "grad_norm": 0.8872298202760914,
532
+ "learning_rate": 1.2652972365459008e-05,
533
+ "loss": 0.7178,
534
+ "step": 370
535
+ },
536
+ {
537
+ "epoch": 0.48,
538
+ "grad_norm": 0.9203346359488073,
539
+ "learning_rate": 1.243658415285622e-05,
540
+ "loss": 0.7384,
541
+ "step": 375
542
+ },
543
+ {
544
+ "epoch": 0.49,
545
+ "grad_norm": 0.8282910946726554,
546
+ "learning_rate": 1.2218976027351177e-05,
547
+ "loss": 0.7138,
548
+ "step": 380
549
+ },
550
+ {
551
+ "epoch": 0.49,
552
+ "grad_norm": 0.8872272744445378,
553
+ "learning_rate": 1.2000256937760446e-05,
554
+ "loss": 0.706,
555
+ "step": 385
556
+ },
557
+ {
558
+ "epoch": 0.5,
559
+ "grad_norm": 0.84010568628107,
560
+ "learning_rate": 1.1780536389121668e-05,
561
+ "loss": 0.7217,
562
+ "step": 390
563
+ },
564
+ {
565
+ "epoch": 0.51,
566
+ "grad_norm": 0.8336774434546579,
567
+ "learning_rate": 1.155992438786818e-05,
568
+ "loss": 0.7431,
569
+ "step": 395
570
+ },
571
+ {
572
+ "epoch": 0.51,
573
+ "grad_norm": 0.8842944246611821,
574
+ "learning_rate": 1.1338531386752618e-05,
575
+ "loss": 0.7203,
576
+ "step": 400
577
+ },
578
+ {
579
+ "epoch": 0.52,
580
+ "grad_norm": 0.898037732512393,
581
+ "learning_rate": 1.1116468229547079e-05,
582
+ "loss": 0.7497,
583
+ "step": 405
584
+ },
585
+ {
586
+ "epoch": 0.52,
587
+ "grad_norm": 0.8824051684243204,
588
+ "learning_rate": 1.0893846095547493e-05,
589
+ "loss": 0.7424,
590
+ "step": 410
591
+ },
592
+ {
593
+ "epoch": 0.53,
594
+ "grad_norm": 0.8537154820589267,
595
+ "learning_rate": 1.0670776443910024e-05,
596
+ "loss": 0.7391,
597
+ "step": 415
598
+ },
599
+ {
600
+ "epoch": 0.54,
601
+ "grad_norm": 0.9527482786635838,
602
+ "learning_rate": 1.0447370957847343e-05,
603
+ "loss": 0.7288,
604
+ "step": 420
605
+ },
606
+ {
607
+ "epoch": 0.54,
608
+ "grad_norm": 0.8801360044023759,
609
+ "learning_rate": 1.0223741488712732e-05,
610
+ "loss": 0.7177,
611
+ "step": 425
612
+ },
613
+ {
614
+ "epoch": 0.55,
615
+ "grad_norm": 0.9017111738645169,
616
+ "learning_rate": 1e-05,
617
+ "loss": 0.7279,
618
+ "step": 430
619
+ },
620
+ {
621
+ "epoch": 0.56,
622
+ "grad_norm": 0.8799316098800196,
623
+ "learning_rate": 9.776258511287271e-06,
624
+ "loss": 0.7172,
625
+ "step": 435
626
+ },
627
+ {
628
+ "epoch": 0.56,
629
+ "grad_norm": 0.8727504370270498,
630
+ "learning_rate": 9.55262904215266e-06,
631
+ "loss": 0.7424,
632
+ "step": 440
633
+ },
634
+ {
635
+ "epoch": 0.57,
636
+ "grad_norm": 0.852138299323907,
637
+ "learning_rate": 9.329223556089976e-06,
638
+ "loss": 0.743,
639
+ "step": 445
640
+ },
641
+ {
642
+ "epoch": 0.58,
643
+ "grad_norm": 0.8429170905572736,
644
+ "learning_rate": 9.10615390445251e-06,
645
+ "loss": 0.7311,
646
+ "step": 450
647
+ },
648
+ {
649
+ "epoch": 0.58,
650
+ "grad_norm": 0.8715107251678864,
651
+ "learning_rate": 8.883531770452924e-06,
652
+ "loss": 0.733,
653
+ "step": 455
654
+ },
655
+ {
656
+ "epoch": 0.59,
657
+ "grad_norm": 0.8309750831558879,
658
+ "learning_rate": 8.661468613247387e-06,
659
+ "loss": 0.726,
660
+ "step": 460
661
+ },
662
+ {
663
+ "epoch": 0.6,
664
+ "grad_norm": 0.8594819292949775,
665
+ "learning_rate": 8.440075612131823e-06,
666
+ "loss": 0.7387,
667
+ "step": 465
668
+ },
669
+ {
670
+ "epoch": 0.6,
671
+ "grad_norm": 0.8578509085890005,
672
+ "learning_rate": 8.219463610878336e-06,
673
+ "loss": 0.7154,
674
+ "step": 470
675
+ },
676
+ {
677
+ "epoch": 0.61,
678
+ "grad_norm": 0.8406550181595651,
679
+ "learning_rate": 7.999743062239557e-06,
680
+ "loss": 0.7044,
681
+ "step": 475
682
+ },
683
+ {
684
+ "epoch": 0.61,
685
+ "grad_norm": 1.1106794650945297,
686
+ "learning_rate": 7.781023972648826e-06,
687
+ "loss": 0.7529,
688
+ "step": 480
689
+ },
690
+ {
691
+ "epoch": 0.62,
692
+ "grad_norm": 0.8787480716579242,
693
+ "learning_rate": 7.563415847143782e-06,
694
+ "loss": 0.7416,
695
+ "step": 485
696
+ },
697
+ {
698
+ "epoch": 0.63,
699
+ "grad_norm": 0.8856437968758147,
700
+ "learning_rate": 7.347027634540993e-06,
701
+ "loss": 0.7234,
702
+ "step": 490
703
+ },
704
+ {
705
+ "epoch": 0.63,
706
+ "grad_norm": 0.9115469753409513,
707
+ "learning_rate": 7.131967672889101e-06,
708
+ "loss": 0.7189,
709
+ "step": 495
710
+ },
711
+ {
712
+ "epoch": 0.64,
713
+ "grad_norm": 0.8461806387832909,
714
+ "learning_rate": 6.918343635227694e-06,
715
+ "loss": 0.739,
716
+ "step": 500
717
+ },
718
+ {
719
+ "epoch": 0.65,
720
+ "grad_norm": 0.8797246523561782,
721
+ "learning_rate": 6.706262475679205e-06,
722
+ "loss": 0.7212,
723
+ "step": 505
724
+ },
725
+ {
726
+ "epoch": 0.65,
727
+ "grad_norm": 0.8833725465549789,
728
+ "learning_rate": 6.495830375900665e-06,
729
+ "loss": 0.7344,
730
+ "step": 510
731
+ },
732
+ {
733
+ "epoch": 0.66,
734
+ "grad_norm": 0.90720732768669,
735
+ "learning_rate": 6.287152691922264e-06,
736
+ "loss": 0.7363,
737
+ "step": 515
738
+ },
739
+ {
740
+ "epoch": 0.67,
741
+ "grad_norm": 0.8562580507509661,
742
+ "learning_rate": 6.080333901399252e-06,
743
+ "loss": 0.714,
744
+ "step": 520
745
+ },
746
+ {
747
+ "epoch": 0.67,
748
+ "grad_norm": 0.8368554839429542,
749
+ "learning_rate": 5.875477551303596e-06,
750
+ "loss": 0.6968,
751
+ "step": 525
752
+ },
753
+ {
754
+ "epoch": 0.68,
755
+ "grad_norm": 0.8551918920773244,
756
+ "learning_rate": 5.672686206081638e-06,
757
+ "loss": 0.7354,
758
+ "step": 530
759
+ },
760
+ {
761
+ "epoch": 0.68,
762
+ "grad_norm": 0.8806502111077001,
763
+ "learning_rate": 5.47206139630363e-06,
764
+ "loss": 0.7009,
765
+ "step": 535
766
+ },
767
+ {
768
+ "epoch": 0.69,
769
+ "grad_norm": 0.8432642364408135,
770
+ "learning_rate": 5.273703567830908e-06,
771
+ "loss": 0.7256,
772
+ "step": 540
773
+ },
774
+ {
775
+ "epoch": 0.7,
776
+ "grad_norm": 0.8082119727212804,
777
+ "learning_rate": 5.077712031526153e-06,
778
+ "loss": 0.7113,
779
+ "step": 545
780
+ },
781
+ {
782
+ "epoch": 0.7,
783
+ "grad_norm": 0.8840305956304885,
784
+ "learning_rate": 4.8841849135319015e-06,
785
+ "loss": 0.7125,
786
+ "step": 550
787
+ },
788
+ {
789
+ "epoch": 0.71,
790
+ "grad_norm": 0.8512866204723579,
791
+ "learning_rate": 4.693219106142186e-06,
792
+ "loss": 0.7077,
793
+ "step": 555
794
+ },
795
+ {
796
+ "epoch": 0.72,
797
+ "grad_norm": 0.8690925493996771,
798
+ "learning_rate": 4.504910219291941e-06,
799
+ "loss": 0.7265,
800
+ "step": 560
801
+ },
802
+ {
803
+ "epoch": 0.72,
804
+ "grad_norm": 0.8486039006714249,
805
+ "learning_rate": 4.319352532688444e-06,
806
+ "loss": 0.7045,
807
+ "step": 565
808
+ },
809
+ {
810
+ "epoch": 0.73,
811
+ "grad_norm": 0.8343157357633112,
812
+ "learning_rate": 4.13663894860873e-06,
813
+ "loss": 0.7081,
814
+ "step": 570
815
+ },
816
+ {
817
+ "epoch": 0.74,
818
+ "grad_norm": 0.8517869372115919,
819
+ "learning_rate": 3.956860945386677e-06,
820
+ "loss": 0.7099,
821
+ "step": 575
822
+ },
823
+ {
824
+ "epoch": 0.74,
825
+ "grad_norm": 0.8810686746902263,
826
+ "learning_rate": 3.7801085316129615e-06,
827
+ "loss": 0.7184,
828
+ "step": 580
829
+ },
830
+ {
831
+ "epoch": 0.75,
832
+ "grad_norm": 0.8303217013600214,
833
+ "learning_rate": 3.606470201070904e-06,
834
+ "loss": 0.7046,
835
+ "step": 585
836
+ },
837
+ {
838
+ "epoch": 0.75,
839
+ "grad_norm": 0.8143514289362858,
840
+ "learning_rate": 3.4360328884307058e-06,
841
+ "loss": 0.7301,
842
+ "step": 590
843
+ },
844
+ {
845
+ "epoch": 0.76,
846
+ "grad_norm": 0.8919694336829919,
847
+ "learning_rate": 3.2688819257242963e-06,
848
+ "loss": 0.7077,
849
+ "step": 595
850
+ },
851
+ {
852
+ "epoch": 0.77,
853
+ "grad_norm": 0.8712369558568198,
854
+ "learning_rate": 3.1051009996225434e-06,
855
+ "loss": 0.7289,
856
+ "step": 600
857
+ },
858
+ {
859
+ "epoch": 0.77,
860
+ "grad_norm": 0.9359803251828337,
861
+ "learning_rate": 2.9447721095362325e-06,
862
+ "loss": 0.7222,
863
+ "step": 605
864
+ },
865
+ {
866
+ "epoch": 0.78,
867
+ "grad_norm": 0.8118275265180527,
868
+ "learning_rate": 2.7879755265618558e-06,
869
+ "loss": 0.6989,
870
+ "step": 610
871
+ },
872
+ {
873
+ "epoch": 0.79,
874
+ "grad_norm": 0.8993664919932826,
875
+ "learning_rate": 2.6347897532926293e-06,
876
+ "loss": 0.7301,
877
+ "step": 615
878
+ },
879
+ {
880
+ "epoch": 0.79,
881
+ "grad_norm": 0.8299858708500569,
882
+ "learning_rate": 2.485291484515e-06,
883
+ "loss": 0.7282,
884
+ "step": 620
885
+ },
886
+ {
887
+ "epoch": 0.8,
888
+ "grad_norm": 0.9509542819405852,
889
+ "learning_rate": 2.339555568810221e-06,
890
+ "loss": 0.7321,
891
+ "step": 625
892
+ },
893
+ {
894
+ "epoch": 0.81,
895
+ "grad_norm": 0.8207790304441084,
896
+ "learning_rate": 2.1976549710802754e-06,
897
+ "loss": 0.704,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 0.81,
902
+ "grad_norm": 0.8915125592646993,
903
+ "learning_rate": 2.0596607360168897e-06,
904
+ "loss": 0.7155,
905
+ "step": 635
906
+ },
907
+ {
908
+ "epoch": 0.82,
909
+ "grad_norm": 0.893971232650736,
910
+ "learning_rate": 1.9256419525319316e-06,
911
+ "loss": 0.7108,
912
+ "step": 640
913
+ },
914
+ {
915
+ "epoch": 0.83,
916
+ "grad_norm": 0.8642943561769831,
917
+ "learning_rate": 1.7956657191669969e-06,
918
+ "loss": 0.7254,
919
+ "step": 645
920
+ },
921
+ {
922
+ "epoch": 0.83,
923
+ "grad_norm": 0.7620702133454862,
924
+ "learning_rate": 1.6697971104994847e-06,
925
+ "loss": 0.701,
926
+ "step": 650
927
+ },
928
+ {
929
+ "epoch": 0.84,
930
+ "grad_norm": 0.9164562019661466,
931
+ "learning_rate": 1.5480991445620541e-06,
932
+ "loss": 0.7252,
933
+ "step": 655
934
+ },
935
+ {
936
+ "epoch": 0.84,
937
+ "grad_norm": 0.86265325973436,
938
+ "learning_rate": 1.4306327512916574e-06,
939
+ "loss": 0.7207,
940
+ "step": 660
941
+ },
942
+ {
943
+ "epoch": 0.85,
944
+ "grad_norm": 0.8591146598972604,
945
+ "learning_rate": 1.3174567420240647e-06,
946
+ "loss": 0.7459,
947
+ "step": 665
948
+ },
949
+ {
950
+ "epoch": 0.86,
951
+ "grad_norm": 0.8261037051966178,
952
+ "learning_rate": 1.2086277800490554e-06,
953
+ "loss": 0.7142,
954
+ "step": 670
955
+ },
956
+ {
957
+ "epoch": 0.86,
958
+ "grad_norm": 0.820114794330799,
959
+ "learning_rate": 1.1042003522410882e-06,
960
+ "loss": 0.7358,
961
+ "step": 675
962
+ },
963
+ {
964
+ "epoch": 0.87,
965
+ "grad_norm": 0.86546920512789,
966
+ "learning_rate": 1.0042267417796292e-06,
967
+ "loss": 0.7088,
968
+ "step": 680
969
+ },
970
+ {
971
+ "epoch": 0.88,
972
+ "grad_norm": 0.8769857056502491,
973
+ "learning_rate": 9.08757001972762e-07,
974
+ "loss": 0.7036,
975
+ "step": 685
976
+ },
977
+ {
978
+ "epoch": 0.88,
979
+ "grad_norm": 0.8727105004473635,
980
+ "learning_rate": 8.178389311972612e-07,
981
+ "loss": 0.7352,
982
+ "step": 690
983
+ },
984
+ {
985
+ "epoch": 0.89,
986
+ "grad_norm": 0.8878216519646419,
987
+ "learning_rate": 7.315180489675822e-07,
988
+ "loss": 0.7161,
989
+ "step": 695
990
+ },
991
+ {
992
+ "epoch": 0.9,
993
+ "grad_norm": 0.8073527792911568,
994
+ "learning_rate": 6.498375731458529e-07,
995
+ "loss": 0.7157,
996
+ "step": 700
997
+ },
998
+ {
999
+ "epoch": 0.9,
1000
+ "grad_norm": 0.8674439240960509,
1001
+ "learning_rate": 5.728383983041696e-07,
1002
+ "loss": 0.6966,
1003
+ "step": 705
1004
+ },
1005
+ {
1006
+ "epoch": 0.91,
1007
+ "grad_norm": 0.8270417868101663,
1008
+ "learning_rate": 5.005590752501244e-07,
1009
+ "loss": 0.7165,
1010
+ "step": 710
1011
+ },
1012
+ {
1013
+ "epoch": 0.91,
1014
+ "grad_norm": 0.8133004838860258,
1015
+ "learning_rate": 4.3303579172574884e-07,
1016
+ "loss": 0.7161,
1017
+ "step": 715
1018
+ },
1019
+ {
1020
+ "epoch": 0.92,
1021
+ "grad_norm": 0.835774320081132,
1022
+ "learning_rate": 3.7030235428956895e-07,
1023
+ "loss": 0.7052,
1024
+ "step": 720
1025
+ },
1026
+ {
1027
+ "epoch": 0.93,
1028
+ "grad_norm": 0.8786655763475584,
1029
+ "learning_rate": 3.1239017139084725e-07,
1030
+ "loss": 0.712,
1031
+ "step": 725
1032
+ },
1033
+ {
1034
+ "epoch": 0.93,
1035
+ "grad_norm": 0.7922242941846357,
1036
+ "learning_rate": 2.593282376444539e-07,
1037
+ "loss": 0.7145,
1038
+ "step": 730
1039
+ },
1040
+ {
1041
+ "epoch": 0.94,
1042
+ "grad_norm": 0.8040418257479052,
1043
+ "learning_rate": 2.11143119314281e-07,
1044
+ "loss": 0.7076,
1045
+ "step": 735
1046
+ },
1047
+ {
1048
+ "epoch": 0.95,
1049
+ "grad_norm": 0.8478224913150121,
1050
+ "learning_rate": 1.6785894101243205e-07,
1051
+ "loss": 0.7232,
1052
+ "step": 740
1053
+ },
1054
+ {
1055
+ "epoch": 0.95,
1056
+ "grad_norm": 0.8323563837704016,
1057
+ "learning_rate": 1.2949737362087156e-07,
1058
+ "loss": 0.7098,
1059
+ "step": 745
1060
+ },
1061
+ {
1062
+ "epoch": 0.96,
1063
+ "grad_norm": 0.8756057853063033,
1064
+ "learning_rate": 9.607762344156946e-08,
1065
+ "loss": 0.734,
1066
+ "step": 750
1067
+ },
1068
+ {
1069
+ "epoch": 0.97,
1070
+ "grad_norm": 0.8581279382569037,
1071
+ "learning_rate": 6.761642258056977e-08,
1072
+ "loss": 0.7192,
1073
+ "step": 755
1074
+ },
1075
+ {
1076
+ "epoch": 0.97,
1077
+ "grad_norm": 0.8325693456753873,
1078
+ "learning_rate": 4.412802057081278e-08,
1079
+ "loss": 0.7203,
1080
+ "step": 760
1081
+ },
1082
+ {
1083
+ "epoch": 0.98,
1084
+ "grad_norm": 0.8361298423651424,
1085
+ "learning_rate": 2.5624177237884017e-08,
1086
+ "loss": 0.7164,
1087
+ "step": 765
1088
+ },
1089
+ {
1090
+ "epoch": 0.99,
1091
+ "grad_norm": 0.7881888700108141,
1092
+ "learning_rate": 1.2114156812284006e-08,
1093
+ "loss": 0.715,
1094
+ "step": 770
1095
+ },
1096
+ {
1097
+ "epoch": 0.99,
1098
+ "grad_norm": 0.8284253094519822,
1099
+ "learning_rate": 3.6047232911462506e-09,
1100
+ "loss": 0.7185,
1101
+ "step": 775
1102
+ },
1103
+ {
1104
+ "epoch": 1.0,
1105
+ "grad_norm": 0.8527930204989956,
1106
+ "learning_rate": 1.0013705174061195e-10,
1107
+ "loss": 0.735,
1108
+ "step": 780
1109
+ },
1110
+ {
1111
+ "epoch": 1.0,
1112
+ "eval_loss": 0.7233731150627136,
1113
+ "eval_runtime": 630.7835,
1114
+ "eval_samples_per_second": 68.169,
1115
+ "eval_steps_per_second": 2.131,
1116
+ "step": 781
1117
+ },
1118
+ {
1119
+ "epoch": 1.0,
1120
+ "step": 781,
1121
+ "total_flos": 80937303736320.0,
1122
+ "train_loss": 0.7476945167619654,
1123
+ "train_runtime": 7284.6392,
1124
+ "train_samples_per_second": 13.727,
1125
+ "train_steps_per_second": 0.107
1126
+ }
1127
+ ],
1128
+ "logging_steps": 5,
1129
+ "max_steps": 781,
1130
+ "num_input_tokens_seen": 0,
1131
+ "num_train_epochs": 1,
1132
+ "save_steps": 100,
1133
+ "total_flos": 80937303736320.0,
1134
+ "train_batch_size": 16,
1135
+ "trial_name": null,
1136
+ "trial_params": null
1137
+ }